ClawHub
Back to skill

Security audit

CodeRabbit

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed CodeRabbit connector wrapper with powerful organization actions, but its behavior is coherent and it requires confirmation for state-changing operations.

Install this only if you want agents to manage CodeRabbit through your OOMOL-connected account. Review prompts carefully before approving role, seat, or deletion actions, because those can affect many organization users.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
84% confidence
Finding
The manifest description says to use this skill for ANY CodeRabbit request and instead of calling the API directly, which is an overly broad trigger that can cause the agent to invoke the skill in situations where more specific review or safer alternatives would be appropriate. Because this skill exposes both read and write/destructive CodeRabbit actions, broad auto-routing increases the chance of unnecessary access, accidental state changes, or use in contexts the user did not explicitly intend.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal